More The TWIML AI Podcast episodes
Published 29 Jan 2026
Duration: 3981
Language models can struggle to generate diverse responses, despite adjustments, and improving their performance requires addressing data quality and training techniques.
Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University in the Computer Science Department and the Institute for Human-C...
The podcast examines how both small and large language models tend to generate similar, homogeneous outputs in response to open-ended prompts, even when temperature settings are modified to encourage diversity. It investigates research efforts aimed at improving small language models (SLMs) by refining their reasoning abilities through methods like better data curation, synthetic data generation, and hybrid model designs. The discussion points out the limitations of relying on internet-based training data and stresses the value of high-quality, specialized content created by humans to train SLMs more effectively.
The podcast also reviews techniques such as imitation learning, reinforcement learning with verification, and data filtering to enhance model performance and output diversity. Additionally, it raises broader concerns about the effects of AI on human creativity and thought, as well as the potential for AI to contribute to the homogenization of online content. Emphasis is placed on the importance of making AI more accessible, exploring diverse alignment approaches, and developing systems that are more data-efficient and ethically responsible.
27 Jul 2026 Why Models Are AIs Next Training Dataset with Damian Borth
"Explores weights-based learning, treating neural network weights as input data to train new models, improving efficiency, addressing data scarcity, and enabling tasks like model compression and performance prediction, with future directions in scaling, privacy, and cross-domain knowledge transfer."
8 Jul 2026 How AI Learns to Smell with Alex Wiltschko
Digitizing scent using AI involves converting molecules into digital data, creating standardized scent representations, and reproducing odors, addressing biological complexities, leveraging graph neural networks, and exploring applications in fragrance, diagnostics, and emotion while highlighting technical and ethical challenges.
9 Jun 2026 Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut
The podcast examines Retrieval-Augmented Generation's evolving role in AI-driven tax compliance, focusing on Spheres AI's TRAM model, challenges in processing fragmented legal data, and the need for accurate citations, taxonomy integration, and real-time compliance automation via a global tax legislation index.
21 May 2026 Relational Foundation Models for Enterprise Data with Jure Leskovec
Relational foundation models and graph-based machine learning, like GNNs, enable accurate predictions on structured data across biomedical research and industries by capturing complex relationships, integrating multi-scale data, and overcoming traditional limitations through automated feature extraction and hybrid modeling.
7 May 2026 How to Find the Agent Failures Your Evals Miss with Scott Clark
Distributional employs post-production analytics, unsupervised learning, and LLMs to analyze agent traces, detect patterns and anti-patterns like hallucinations, address distributional shifts, and generate actionable insights for AI system refinement in security and enterprise settings, emphasizing adaptive analytics and domain expertise.